© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41602
    Prev
    Next
    INDEX
    Explanations

    events and submissions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -LAST
    -0.28
    -first
    -0.27
     isFirst
    -0.27
     standoff
    -0.27
    第ä¸Ģ
    -0.26
    maf
    -0.26
     slee
    -0.26
    é¦ĸ款
    -0.26
    	first
    -0.26
    _FIRST
    -0.25
    POSITIVE LOGITS
     virtual
    0.33
     Features
    0.32
     well
    0.30
     offering
    0.30
     quarterly
    0.28
    features
    0.27
    ivating
    0.27
    å¼ĢæĶ¾
    0.27
    virtual
    0.26
     web
    0.26
    Activations Density 0.007%

    No Known Activations